agentsclimarketplace
Sign in

Landing page generator

Skill tmj-90/gaffer/runner/skills/landing-page-generator

Use when asked to create a landing page, marketing page, homepage, lead-capture page, campaign page, or conversion-optimised web page. Outputs complete Next.js/React (TSX) + Tailwind CSS components with proven copy frameworks (PAS/AIDA/BAB), SEO meta tags, and Core Web Vitals targets. Triggers on "create a landing page", "marketing page", "homepage", "lead gen page", or "conversion page".From its SKILL.md

Install
npx -y skills add tmj-90/gaffer --skill landing-page-generator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.7 KB, 810 tokens by cl100k_base, as published. Nobody here has run it

Generate high-converting landing pages

Not lorem ipsum — actual copy and structure that converts. Output complete, ready-to-ship TSX components with Tailwind.

Performance targets: LCP ≤ 2.5s · CLS < 0.1 · INP < 200ms

Copy frameworks

Pick one per page — don't mix:

FrameworkStructureBest for
PASProblem → Agitate → SolutionPain-aware traffic; problem-first messaging
AIDAAttention → Interest → Desire → ActionCold traffic; brand-new product
BABBefore → After → BridgeTransformation products; outcome-led

Section blueprint (in order)

  1. Hero — headline (value prop in ≤ 10 words) + subheadline (1 sentence expanding on the outcome) + primary CTA + social proof signal (count or logo strip).
  2. Problem / Pain — articulate the cost of the status quo in the user's own language.
  3. Solution / Features — 3–6 benefits (not feature names); each benefit has a one-line explanation.
  4. Social proof — testimonials with name, role, company; star ratings if applicable; logos.
  5. Pricing (if applicable) — 2–4 tiers; highlight the recommended one; FAQ accordion.
  6. FAQ — answer the 5 objections that would stop a user converting; include FAQ schema markup.
  7. Footer CTA — repeat the primary CTA; reduced friction (email-only, not full form).

Steps

  1. Gather inputs. Before writing: product name, tagline, primary audience, key pain point, main benefit, primary CTA label, design style (pick one: minimal light / editorial dark / neo-brutalist / SaaS clean). Ask for missing fields — one question at a time.
  2. Choose copy framework. Based on traffic source and audience awareness level.
  3. Write copy first, structure second. Headline variants: write 5, pick the clearest (not the cleverest). Subheadline must state the outcome, not the mechanism.
  4. Build sections in order. Hero → social proof → problem → solution → pricing → FAQ → footer CTA. Each section is a standalone TSX component.
  5. SEO meta. Title tag (≤ 60 chars), meta description (≤ 160 chars), OG tags, canonical.
  6. Performance. Hero image: loading="eager" fetchpriority="high". Everything below the fold: loading="lazy". Fonts: font-display: swap; preload only the critical weight.
  7. Verify. Type-check (tsc --noEmit); Lighthouse score on desktop; confirm LCP < 1s; record evidence.

Build / Test

  • tsc --noEmit — zero type errors.
  • Lighthouse desktop: Performance ≥ 90, Accessibility ≥ 90, Best Practices ≥ 90.
  • Validate structured data with Google Rich Results Test (FAQ schema).

Review checklist

  • Headline states outcome — not the product name or a feature.
  • CTA above the fold — visible without scrolling on 1440px viewport.
  • Social proof specific — names, roles, companies (not generic "thousands of customers").
  • Mobile layout tested — 375px and 768px viewports; no overflow.
  • Hero image performance — eager/high priority; next-gen format (AVIF/WebP).
  • No lorem ipsum — every placeholder replaced with real or clearly marked copy.

References

references/copy-frameworks.md — PAS/AIDA/BAB templates with fill-in-the-blank examples.

What ships with it: 1 file

1.8 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most marketing audience skills give in 810 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • choose a single copy framework per page
  • write five headline variants and pick the clearest
  • build each section as a standalone TSX component
  • include SEO meta tags and OG tags
  • optimize images with explicit loading and fetchpriority attributes
  • preload only critical font weights

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.